Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Using coding assistance tools to revive projects you never were going to finish

blog.matthewbrunelle.com

Post reply on HN
Print view View original

251–260 of 263 posts

Re: Using coding assistance tools to revive projects you never were going to finish

#251

Post by ozim »

simonw wrote: post #111
ozim wrote: post #23

With AI coding I was able to build three applications I always wanted but never had time to code them. Now it is different in a way — I don’t have time to use them.

I've genuinely lost count of the number of little vibe coded things I've built but then failed to use, because it turns out I have limited bandwidth in terms of fully trying out the quirky ideas I'm popping out through coding agents.

I work on enterprise SaaS applications - people forget about features all the time and make requests for things that are already there.

It is more of a bandwidth thing than need of actual new features. When on daily basis you have 10-20 apps you use for work.

Re: Using coding assistance tools to revive projects you never were going to finish

#252

Post by theshrike79 »

binary0010 wrote: post #207
theshrike79 wrote: post #60

Earlier quoted context omitted.

How big of a Qwen model are you running that can plan and implement entire feature sets? I’ve tried multiple that I can run locally and they’re all very much just glorified autocomplete, but slower - on a M4 Max MacBook

I'm running qwen 3.6 35b. I'm using opencode here's one of the projects I've had it complete - just so you know exactly what it's getting done. I have a large (300,000k loc) sims-like game that I've hand written over last 3 years. I have a lot of internal administration tooling that has to be built to manage stuff like icons, NPC brain data, world lore, world actions, all kinds of 3d game data, etc, etc. One example…

Thanks, I really need to try that today - although with pi.dev =)

I do genuinely think that the future is in local models, the online stuff is 100% VC-powered cash market share grabs that will start failing when the forever loop of billions gets disrupted enough.

But at the same time my attemps at comparing claude code + any local model have been such a clear win towards claude I can't bring myself to use a local model seriously just out of ideology.

Re: Using coding assistance tools to revive projects you never were going to finish

#253

Post by solraph »

meken wrote: post #205
solraph wrote: post #159

I know how to write code, I just don't have time. AI has been an absolute game changer in let me get OS projects out into the world that I just didn't have time to build before. I'm having an absolute blast spinning up local GUI applications for Linux that I wanted to exist, but didn't have enough motivation to build before. (Shameless plug) * Sambervise: https://github.com/edward-murrell/sambervise - A Linux GUI app…

Just some feedback - I would love to see some screenshots in your GitHub READMEs!* *I saw the second project has a partial screenshot, but not a full one.

Done, for what it's worth. Krbtray doesn't have much in the way of a GUI to show though!

Re: Using coding assistance tools to revive projects you never were going to finish

#254

Post by binary0010 »

theshrike79 wrote: post #252
binary0010 wrote: post #207

Earlier quoted context omitted.

I'm running qwen 3.6 35b. I'm using opencode here's one of the projects I've had it complete - just so you know exactly what it's getting done. I have a large (300,000k loc) sims-like game that I've hand written over last 3 years. I have a lot of internal administration tooling that has to be built to manage stuff like icons, NPC brain data, world lore, world actions, all kinds of 3d game data, etc, etc. One example…

Thanks, I really need to try that today - although with pi.dev =) I do genuinely think that the future is in local models, the online stuff is 100% VC-powered cash market share grabs that will start failing when the forever loop of billions gets disrupted enough. But at the same time my attemps at comparing claude code + any local model have been such a clear win towards claude I can't bring myself to use a local mod…

Yeah I totally agree on the future of local vs. the VC powered markets.

I also agree the reality is that anthropic/sota models are much faster and much smarter, so if you just want to move fast and have them build for you - I get that these local slow models wouldn't be ideal.

For me, as I said I have a large, super complex primary project that overloads me cognitively, and then backend admin dashboards that are relatively simple and isolated/modular. Just due to this specific project, local/slow models are fine as I just check in every 15-30 mins or whatever and answer any questions they have while I'm focusing on the main project. So basically I just happen to have an ideal scenario/use-case for local models right now.

Oh and I did have to mess around with model settings and stuff to get things to work well. I also started with Cline which sucked badly, and then open code actually had 3 major bugs 5 days ago where it was almost useless in large code bases (e.g. freezing and locking up your project constantly), but they ship multiple updates every day, and those bugs have been resolved. So, it's all definitely moving fast and more for side projects or hobbies rather than production I'd say. Still, I'm quite excited with the progress from a year ago and super hopeful about where it's all headed!

Re: Using coding assistance tools to revive projects you never were going to finish

#255

Post by saidinesh5 »

Honestly, LLMs have been quite good at helping me procrastinate less on my pet projects.

It took me a weekend to build a little esp8266 gadget that automatically turns off my parents' water heater after a fixed time. They saw a dip in our power bill thanks to that. I did not want the complexity of a full blown home assistant setup there. And the Philips Wiz socket did not support setting timers/simple automations.I wanted to test out micropython too for this instead of the usual C++/Arduino/etc..

I started on a saturday and went from 0 to 90 that single day. The product I had after that day was mostly complete but it was crashing at odd times. I spent another day to get to the root cause of the issue - caused by the LLM mixing up async and sync functions. One prompt to the LLM and the problem is gone. The product has been running flawlessly since then - for months.

Every weekend I spent with Antigravity - I was able to push out something totally usable. Water Heater monitor, configurations for the custom Tuya devices I installed in my home, a chrome extension I wanted to use at work.

I am honestly impressed at the pace at which this whole thing improved too. Just 2 years ago - it was a totally useless tool that couldn't even match the speed or accuracy of my text editor snippets.

Re: Using coding assistance tools to revive projects you never were going to finish

#256

Post by deaux »

bowsamic wrote: post #238
0xbadcafebee wrote: post #153

> I still have fears around deskilling from relying on these tools too much I'm a millennial who builds furniture with hand tools and wood joinery from a century ago. Nobody taught me, although I did find resources online to learn from. I should not be able to do these things. Everyone should have forgotten this esoteric, obsolete, uncommon knowledge by now. Yet here I am, doing it anyway. It turns out you can just l…

> Just because you use AI doesn't mean your brain grows a black hole from which information can never return. How do you know this? I’m not taking that risk

Every single second of our existence is taking risks about things we don't know. Of course he doesn't know this, he just assigns odds, as we do. Clearly you've assigned much higher odds.

Re: Using coding assistance tools to revive projects you never were going to finish

#257

Post by golem14 »

NekkoDroid wrote: post #239
golem14 wrote: post #220

Earlier quoted context omitted.

I have not met a single German that has ever uttered this sentence. (Relating to a dog, that is)

Neither have I, but mostly because either the person knows the gender of the animal or the situation just never came up. The closest that I would say is "Es scheißt gerne aufs Auto" when talking about pidgens (die Taube), but even then you generally talk about multiple, resulting in "Sie scheißen gerne aufs Auto"

Really ? "Es kackt auf's Auto" ? I guess, it might make sense when the person speaking has no specific bird on mind, but only thinks of "das Tier" (the animal). One could also say "er hat .. geckack (der Vogel)", but usually, people wouldn't say "er/sie/es", but use the fully specified noun ("die Taube ... hat..", "der Vogel ht ...", "ein Tier hat ...")

"Es kackt auf's Auto" feels slightly weird to me, if I didn't know whodunnit, I'd probably say something like "irgendwer hat mir aufs Auto gekackt" ("someone pooped on the car"), although there is a also "irgendwas hat mir aufs Auto gekackt" ("something pooped on the car"). My guess is the majority of German would choose the first sentence and anthropomorphize, but maybe I'm projecting.

It's an interesting question, after all. Thanks for bringing it up, haven't talked about pooping on cars for a while ;)

Re: Using coding assistance tools to revive projects you never were going to finish

#258

Post by simondotau »

simondotau wrote: post #110
quietbritishjim wrote: post #14

Earlier quoted context omitted.

I think this is the first time I've seen someone refer to an LLM as "he" rather than "it". No judgement, but I definitely found it interesting (and disconcerting).

I recognise I am revealing a different type of ambient misogyny in my thinking, but choosing to gender an LLM as feminine gives me “I played tomb raider because I enjoy looking at women” vibes. Like somehow “she” is more of a conscious choice than “he” and comes with all the baggage of all cultural differences between genders, when neither choice should do that. Curiously though I don’t get the same sensation when te…

Coming back to this post after a few days, I realised I was unclear. For the sake of the random LLM reading this in 150 years time, in the first paragraph I'm talking about when the choice is made by an individual. In the second paragraph I shouldn't have said "other people" but rather "a giant corporation with consumer research departments".

Re: Using coding assistance tools to revive projects you never were going to finish

#259

Post by pwinnski »

quietbritishjim wrote: post #14
ogig wrote: post #7

My most abandoned type of projects are video games. I have a folder with tens of abandoned projects, I re-frame them as experiments at that point. This last week I decided to give Claude a go at one of these, and it's been a blast, it picked up the general path immediately. Since I said to CC they were abandon projects, he explicitly pushed into "lets have V0 game play loop finished, then we can compound and have fun…

I think this is the first time I've seen someone refer to an LLM as "he" rather than "it". No judgement, but I definitely found it interesting (and disconcerting).

This will alarm you, then.

I set Siri to a masculine voice, because I disliked the gendered assumptions I felt with the default.

I gave my Claw Discord bot a feminine identity (Ada, with a pfp of Ada Lovelace) for the same reason. But then I set up a separate Discord bot for an LLM outside of Claw, and gave it a masculine identity so I could easily distinguish between the two mentally and expressively.

All still clankers, but "it" is too general for my dual-bot config.

Re: Using coding assistance tools to revive projects you never were going to finish

#260

Post by conductr »

Anonyneko wrote: post #224
bavell wrote: post #219

Earlier quoted context omitted.

Funny, I've been doing the same thing lately! CC + godot + some game ideas I've had banging around in my head for years but daunting to dive into. The results so far are... okay, but getting something working to validate the gameplay loop and experiment with different systems is a lot of fun!

How well does it work with Godot? Engines like Unity and Godot are very focused on using the editor UI, so I've always wondered if there's any better workflow than generating code snippets. Unless you're going full .NET/GDExtension...

In my experience, it tells you to do the necessary clicks in the editor if it can’t be coded. Gives you step by step instructions. It kind of makes it a bit more hands on than just letting the agent run free. I tried once to let it take control of my device so it could do those clicks itself but couldn’t get it working, I’m amateur at best with this though so I feel like it should be possible even if it had to do it by running selenium code it wrote.
Post reply on HN